Writing logs to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:rte-2020-06-29-13:10/log.txt.
Loading [94mnlp[0m dataset [94mglue[0m, subset [94mrte[0m, split [94mtrain[0m.
Loading [94mnlp[0m dataset [94mglue[0m, subset [94mrte[0m, split [94mvalidation[0m.
Loaded dataset. Found: 2 labels: ([0, 1])
Loading transformers AutoModelForSequenceClassification: xlnet-base-cased
Tokenizing training data. (len: 2490)
Tokenizing eval data (len: 277)
Loaded data and tokenized in 14.161188840866089s
Training model across 1 GPUs
***** Running training *****
	Num examples = 2490
	Batch size = 16
	Max sequence length = 128
	Num steps = 775
	Num epochs = 5
	Learning rate = 2e-05
Eval accuracy: 54.151624548736464%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:rte-2020-06-29-13:10/.
Eval accuracy: 66.06498194945848%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:rte-2020-06-29-13:10/.
Eval accuracy: 65.70397111913357%
Eval accuracy: 71.11913357400722%
Best acc found. Saved model to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:rte-2020-06-29-13:10/.
Eval accuracy: 71.11913357400722%
Saved tokenizer <textattack.models.tokenizers.auto_tokenizer.AutoTokenizer object at 0x7fd4a0851e80> to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:rte-2020-06-29-13:10/.
Wrote README to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:rte-2020-06-29-13:10/README.md.
Wrote training args to /p/qdata/jm8wx/research/text_attacks/textattack/outputs/training/xlnet-base-cased-glue:rte-2020-06-29-13:10/train_args.json.